Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Designing an AI-Enhanced Interface for Cognitive Support in High-Stakes Interrogations

Roxhage, André LU and Ahlström, Jonathan LU (2026) MAMM01 20261
Ergonomics and Aerosol Technology
Certec - Rehabilitation Engineering and Design
Abstract
Interrogation leaders in high-stakes investigative settings must convert long
interview sessions into accurate written protocols under time pressure, stress,
and cognitive bias. While AI has the potential to streamline this work, generic
large-model assistants risk replacing one form of cognitive effort with another
by inviting passive acceptance of generated output. To address this, we de-
signed, developed, and evaluated FENRIR, a locally hosted AI product that
supports post-interview documentation. We then assessed how well FENRIR
fits the workflow of interrogation leaders at an authority that conducts such
investigations. We followed a user-centered design process and developed
FENRIR in cooperation with a domain expert and... (More)
Interrogation leaders in high-stakes investigative settings must convert long
interview sessions into accurate written protocols under time pressure, stress,
and cognitive bias. While AI has the potential to streamline this work, generic
large-model assistants risk replacing one form of cognitive effort with another
by inviting passive acceptance of generated output. To address this, we de-
signed, developed, and evaluated FENRIR, a locally hosted AI product that
supports post-interview documentation. We then assessed how well FENRIR
fits the workflow of interrogation leaders at an authority that conducts such
investigations. We followed a user-centered design process and developed
FENRIR in cooperation with a domain expert and interrogation leaders from
the studied organization. Participants agreed that transcript traceability of AI-
based analysis was essential, and reported that AI-assisted analysis shifted
their effort from generation to verification rather than removing effort alto-
gether. Building on this, we argue for further work on so-called frictional
design, interface patterns that make verification a required step of the work-
flow rather than one the user can skip, so that the human remains the final
decision-maker, particularly in high-stakes investigative settings. (Less)
Please use this url to cite or link to this publication:
author
Roxhage, André LU and Ahlström, Jonathan LU
supervisor
organization
course
MAMM01 20261
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Investigative interviewing, AI, Local LLM, Frictional design, Human-in- the-loop, Cognitive load, Interrogation protocol drafting
language
English
id
9230187
date added to LUP
2026-06-04 11:21:47
date last changed
2026-06-04 11:21:47
@misc{9230187,
  abstract     = {{Interrogation leaders in high-stakes investigative settings must convert long
interview sessions into accurate written protocols under time pressure, stress,
and cognitive bias. While AI has the potential to streamline this work, generic
large-model assistants risk replacing one form of cognitive effort with another
by inviting passive acceptance of generated output. To address this, we de-
signed, developed, and evaluated FENRIR, a locally hosted AI product that
supports post-interview documentation. We then assessed how well FENRIR
fits the workflow of interrogation leaders at an authority that conducts such
investigations. We followed a user-centered design process and developed
FENRIR in cooperation with a domain expert and interrogation leaders from
the studied organization. Participants agreed that transcript traceability of AI-
based analysis was essential, and reported that AI-assisted analysis shifted
their effort from generation to verification rather than removing effort alto-
gether. Building on this, we argue for further work on so-called frictional
design, interface patterns that make verification a required step of the work-
flow rather than one the user can skip, so that the human remains the final
decision-maker, particularly in high-stakes investigative settings.}},
  author       = {{Roxhage, André and Ahlström, Jonathan}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Designing an AI-Enhanced Interface for Cognitive Support in High-Stakes Interrogations}},
  year         = {{2026}},
}